flyrain commented on code in PR #4539: URL: https://github.com/apache/iceberg/pull/4539#discussion_r854665830
########## spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/BaseCdcSparkAction.java: ########## @@ -0,0 +1,262 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +package org.apache.iceberg.spark.actions; + +import java.util.List; +import java.util.Set; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.iceberg.BaseFileScanTask; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataOperations; +import org.apache.iceberg.FileContent; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.ManifestFile; +import org.apache.iceberg.ManifestGroup; +import org.apache.iceberg.MetadataColumns; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.Cdc; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.FileScanTaskSetManager; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.iceberg.util.SnapshotUtil; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.functions; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.apache.spark.sql.functions.lit; + +public class BaseCdcSparkAction extends BaseSparkAction<Cdc, Cdc.Result> implements Cdc { + private static final Logger LOG = LoggerFactory.getLogger(BaseCdcSparkAction.class); + public static final String RECORD_TYPE = "_record_type"; + public static final String COMMIT_SNAPSHOT_ID = "_commit_snapshot_id"; + public static final String COMMIT_TIMESTAMP = "_commit_timestamp"; + public static final String COMMIT_ORDER = "_commit_order"; + private final List<Long> snapshotIds = Lists.newLinkedList(); + private final Table table; + private final List<Dataset<Row>> dfs = Lists.newLinkedList(); + private boolean ignoreRowsDeletedWithinSnapshot = true; + + private Expression filter = Expressions.alwaysTrue(); + + protected BaseCdcSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + } + + @Override + public Result execute() { + // use the current snapshot by default + if (snapshotIds.isEmpty()) { + if (table.currentSnapshot() != null) { + snapshotIds.add(table.currentSnapshot().snapshotId()); + } + } + + for (int i = 0; i < snapshotIds.size(); i++) { + generateCdcRecordsPerSnapshot(snapshotIds.get(i), i); + } + + Dataset<Row> outputDf = null; + for (Dataset<Row> df : dfs) { + if (outputDf == null) { + outputDf = df; + } else { + outputDf = outputDf.unionByName(df, true); + } + } + return new BaseCdcSparkActionResult(outputDf); + } + + private void generateCdcRecordsPerSnapshot(long snapshotId, int commitOrder) { + Snapshot snapshot = table.snapshot(snapshotId); + if (snapshot.operation().equals(DataOperations.REPLACE)) { + return; + } + + // new data file as the insert + Dataset<Row> df = readAppendDataFiles(snapshotId, commitOrder); + if (df != null) { + dfs.add(df); + } + + // metadata deleted data files + Dataset<Row> deletedDf = readMetadataDeletedFiles(snapshotId, commitOrder); + if (deletedDf != null) { + dfs.add(deletedDf); + } + + // pos and eq deletes + Dataset<Row> rowLevelDeleteDf = readRowLevelDeletes(snapshotId, commitOrder); + if (rowLevelDeleteDf != null) { + dfs.add(rowLevelDeleteDf); + } + } Review Comment: I can definitely make the change. Although, I don't think it makes any difference. Basically, these cdc records(e.g. `1, aa, D`, `1, bb, I` ) **within a snapshot** doesn't have any order. Please check the discussion in the [design doc](https://docs.google.com/document/d/1bN6rdLNcYOHnT3xVBfB33BoiPO06aKBo56SZmuU9pnY/edit#heading=h.czd6l3c9xj87). We should treat them same in term of order while ingesting them into downstream. Here, we cannot delete the row (`1, aa`) by just checking its id, instead, we may delete it by checking both values. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
